Deploying Slack Gateway for Amazon Bedrock

In today's fast-changing digital world, streamlining workflows and increasing productivity is paramount. That's why we're excited to bring you an exciting integration that will take team collaboration to a new level. Get ready to unleash the power of generative artificial intelligence (AI) and bring it directly into your Slack workspace.

Imagine the possibilities: fast and efficient brainstorming sessions, real-time ideation, and even drafting documentation and code snippets, all powered by the latest advancements in AI. Say goodbye to context switching and enjoy a streamlined collaborative experience that supercharges your team's productivity. Whether you lead a dynamic team, are working on complex projects, or simply want to enhance your Slack experience, this integration is a game-changer.

In this post, we show you how you can use Amazon Bedrock to bring the power of generative AI directly into your Slack workspace, helping to take efficiency and creativity to new levels.

Solution overview

Amazon Bedrock is a fully managed service that offers a choice of high-performance foundational models (FMs) from leading AI companies such as AI21 Labs, Anthropic, Cohere, Meta, Stability AI, and Amazon through a single API and also provides a wide range of capabilities for building generative AI applications with security, privacy, and responsible AI.

The following sections guide you through the process of setting up the Slack integration for Amazon Bedrock by showing you how to create a Slack application, configure the required permissions, and deploy the required resources using AWS CloudFormation.

The following diagram shows the solution architecture:

The workflow consists of the following steps:

1. Users communicate with the Slack application.
2. The Slack application sends events to an Amazon API Gateway, which is used for event subscriptions.
3. API Gateway forwards the event to an AWS Lambda function.
4. The Lambda function calls Amazon Bedrock with the request and responds to the user in Slack.

Prerequisites

To create and manage the resources and components required for this application, you need an AWS account and a user with AWS Identity and Access Management (IAM) roles and permissions. If you don't have an AWS account, see How do I create and activate a new Amazon Web Services account?

You also need an existing account with permissions to access the Amazon Bedrock model. If you don't have permissions to access the model, see Accessing a Model.

Finally, you'll need a Slack account and access to create and publish apps in a Slack organization. If you don't have one, you can either ask your company to create a Slack sandbox organization for you to experiment with, or go to Slack and create a free Slack account and workspace.

Create a Slack Application

Security configurations vary by organization. To manage the settings for your Slack workspace, contact your Slack admin or follow these steps as an admin:

1. Go to the Admin section in Slack build.
   
2. choose Create a new app.
   
3. for app nameEnter the name of the app (in this article BedrockSlackIntegration).
4. Select a workspace.
5. choose Create an app.
   
   Once you create an app, you can configure its permissions.
6. On the app details page, basic information In the navigation pane.
7. under Adding Featureschoose authority
   
8. In scope Add scopes in the section im:read, im:writeand chat:write.
   

upper basic information page, Bots and authority Both should have a green check mark.

9. under Install the appchoose Install to workspace.
   
10. When you are prompted to install To give permission.
    
11. Open the Amazon Bedrock console, Model Access In the navigation pane.
    
12. You can select a model from the available list. For this post, we grant access to ai21.j2-ultra-v1 (Jurassic-2 Ultra). For more information about requesting model access, see Model Access. Next, we deploy the code and connect to Amazon Bedrock when it receives a message from Slack. To do this, we need the Slack bot token, which we use as an input parameter for the CloudFormation template in the next section.
13. On the Slack app details page, OAuth and Authorization In the navigation pane.
14. Copy the value of The OAuth token for the bot user.
    

Deploying resources with AWS CloudFormation

To launch the CloudFormation stack, complete the following steps:

1. for Stack NameUse the default or enter a name of your choice.
2. for Slack Token Parameterand enter the bot token you copied earlier.
3. choose Next.
   
4. Create the stack and wait a few minutes for the deployment to complete.
   
5. upper output Copy the tab value SlackBotEndpointOutput You will use it in the next step.
   

In the next section, we'll get started integrating Amazon Bedrock with Slack.

Integrate Amazon Bedrock with Slack

After you deploy the CloudFormation stack, complete the following steps:

1. On the Slack app details page, Event Subscription In the navigation pane.
2. toggle Enable events upon.
   

Event subscriptions are validated automatically.

3. Add an event with Bot Event Subscription app_mention and message.im.
4. [変更を保存]Choose.
   
   The integration is complete.

Test your Slack bot

To test your bot, follow these steps:

1. Navigate slack.
2. Create a new group and add an app BedrockSlackIntegration.
3. To start interacting with your Amazon Bedrock bot @BedrockSlackIntegration.

The interaction will look like the following screenshot:

The bot presented here does not store chat history, including the state of previous questions or subsequent new messages, but you can implement this using Amazon DynamoDB, which we will cover in a later blog post.

summary

In this post, we detailed the seamless integration between Amazon Bedrock and the popular collaboration platform Slack. Our step-by-step guide showed you how to directly connect these two powerful tools to unlock the full potential of generative AI, directly within your Slack workspace. This integration streamlines your workflow to increase productivity and makes it easy to take advantage of the cutting-edge capabilities of generative AI. Whether you're generating content, analyzing data, or exploring innovative ideas, this integration lets you do it all without leaving the familiar Slack environment.

You can further empower your teams by deploying Slack Gateway for Amazon Q Business, a generative AI assistant that helps employees based on the knowledge and data in your enterprise systems. To learn more about using generative AI with AWS services, see Generative AI on AWS.

---

About the Author

Rushabh Lokhande He is a Senior Data & ML Engineer in the AWS Professional Services Analytics practice, helping customers implement big data, machine learning, analytical, and generative AI solutions. Outside of work, he enjoys spending time with his family, reading, running, and golfing.

Andrew Ang He is a Senior ML Engineer in the AWS Generative AI innovation center, helping customers ideate and implement Generative AI proof-of-concept projects. Outside of work, he likes playing squash, traveling and watching food vlogs.

John Rosito As an Associate Cloud Infrastructure Architect with AWS Professional Services, I help clients write automation scripts using AWS CDK or Terraform to efficiently deploy and manage cloud resources. Outside of work, I like to spend time with my family, exercise, and hone my archery skills.